RagRetrievalEvaluation
Hybrid search for RAG: what BM25 actually bought us
We added BM25 to a dense retriever across ten probes. It moved two of them, and seven were already saturated. What that means before you build it.
Tag
Rag
7posts tagged Rag. All posts
RagEvaluationRetrieval
A RAG benchmark is only worth running if it can fail
A benchmark that cannot fail is measuring whether you wrote a hard question. The armed-probe rule, and the counts that show whether yours is armed.
RagRetrievalEvaluation
RAG chunk size and overlap: what each one actually bought
Changing the splitter recovered 19 of 25 answers. Adding overlap on top recovered 6 more, and none of them for the reason overlap is sold on.
RagCost optimisationLlm operations
RAG cost: what a query actually spends, counted not estimated
Token accounting for a local RAG pipeline: what k costs, where prompt tokens go, what the template tax is, and the formula to price it on any provider.
RagEvaluationRetrieval
RAG evaluation: how to test a stack that fails quietly
A method for evaluating RAG that survives a real corpus: armed probes, controls first, and retrieval failures counted apart from generation failures.
RagEvaluationRetrieval
RAG evaluation metrics: four ways a good score misleads
Saturation, partial credit, abstention counted as a catch, and detectability without power. Four ways a RAG metric reports a result it did not earn.
RagEvaluationGuardrails
RAG hallucination: what a citation check actually catches
We built the cheap guardrail, checking a cited chunk holds the value the answer asserts, then measured it against the answer failures of four configs.